Paraphrase Identification Based on Interpretable Mechanism
- Resource Type
- Conference
- Authors
- Li, Lin; Lai, BinBin; Huang, JiangPing
- Source
- 2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture (AIAM) AIAM Artificial Intelligence and Advanced Manufacture (AIAM), 2021 3rd International Conference on. :416-421 Oct, 2021
- Subject
- Computing and Processing
Dictionaries
Text recognition
Bit error rate
Semantics
Neural networks
Natural languages
Forestry
paraphrase identification
interpretable mechanism
vector representation
- Language
Paraphrase identification is an important branch of natural language understanding. This paper proposes a vector representation method integrating explanatory text by adding the semantic features of explanatory text to the word vector representation, the vector representation integrates the common interpretation information of words outside the sentence, so as to enrich the semantics of vector representation. This paper obtains explanatory texts from the corpus of Modern Chinese Dictionary. Using a variety of neural network structures on the LCQMC, this work obtained more than 1% performance improvement with fusing explanatory text. The experimental results show that the vector representation of fused explanatory text is more suitable for the task of paraphrase recognition.